INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ighth

-0.84

uler

-0.77

Published

-0.75

 denomin

-0.74

quished

-0.68

ought

-0.68

pherd

-0.64

ernels

-0.64

 prevailed

-0.63

enegger

-0.63

POSITIVE LOGITS

GI

0.66

tip

0.62

ORY

0.62

 Robo

0.61

 WikiLeaks

0.61

BIL

0.61

sy

0.59

VE

0.59

TPP

0.58

 srfAttach

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.